© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10192
    Prev
    Next
    INDEX
    Explanations

    not followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èł¡
    -0.09
    é©°
    -0.08
     bè
    -0.08
    æŃ£å½ĵ
    -0.08
    ligt
    -0.07
    onas
    -0.07
    ä¸Ģ群
    -0.07
    è£ģ
    -0.07
    usto
    -0.07
    emb
    -0.07
    POSITIVE LOGITS
    éĩİçĶŁåĬ¨çī©
    0.10
    ä¸į代表
    0.09
     Lub
    0.09
    å±±åĿ¡
    0.09
    æľīåĬ©
    0.09
    æĺķ
    0.09
    .external
    0.09
    éĶ¹
    0.08
    è¿Ļä¸įæĺ¯
    0.08
    iture
    0.08
    Activations Density 0.018%

    No Known Activations